# CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

arXiv: https://arxiv.org/abs/2510.20820 · HTML: https://mlsanity.com/paper/2510.20820/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 64 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)
- [Orthogonal Adaptation for Modular Customization of Diffusion Models](https://mlsanity.com/paper/2312.02432/) (2023)
- [Multi-subject Open-set Personalization in Video Generation](https://mlsanity.com/paper/2501.06187/) (2025)
- [OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models](https://mlsanity.com/paper/2403.10983/) (2024)
- [TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space](https://mlsanity.com/paper/2501.12224/) (2025)
- [MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation](https://mlsanity.com/paper/2404.11565/) (2024)
- [LCM-Lookahead for Encoder-based Text-to-Image Personalization](https://mlsanity.com/paper/2404.03620/) (2024)
- [UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization](https://mlsanity.com/paper/2408.05939/) (2024)
- [HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2410.14324/) (2024)
- [LayerDiffusion: Layered Controlled Image Editing with Diffusion Models](https://mlsanity.com/paper/2305.18676/) (2023)
- [CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design](https://mlsanity.com/paper/2505.19114/) (2025)
- [InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity](https://mlsanity.com/paper/2503.16418/) (2025)
- [InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation](https://mlsanity.com/paper/2404.19427/) (2024)

## Built on by (most cited first, 3 of 3)

- [Canvas-to-Image: Compositional Image Generation with Multimodal Controls](https://mlsanity.com/paper/2511.21691/) (2025)
- [AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas](https://mlsanity.com/paper/2603.14770/) (2026)
- [Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation](https://mlsanity.com/paper/2605.26111/) (2026)

## Abstract (arXiv)

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer